Electronic Device for Generating Natural Language Response and Method Thereof

1. An electronic device comprising: an output device; at least one processor operatively connected to the output device; and a memory operatively connected to the at least one processor, wherein the memory is configured to store a plurality of candidate condition tables, wherein the memory is further configured to store instructions that, when executed, cause the at least one processor to: detect occurrence of an event, determine a query corresponding to the event in response to the occurrence of the event, obtain raw data based on at least part of the determined query, determine a main information condition table from among the plurality of candidate condition tables, based on context information associated with the event, for defining a priority condition, determine the priority condition for selecting data from among the obtained raw data, based on the context information associated with the event and based on the main information condition table, select main information from the obtained raw data, based on the priority condition, and output a natural language response generated based on the selected main information, through the output device, and wherein the main information condition table comprises at least one data field item and a priority determination condition corresponding to the respective at least one data field item.

2. The electronic device of claim 1 , wherein the instructions further cause the at least one processor to: determine a main information candidate list including at least one value corresponding to the at least one data field item, and select the main information among the at least one value based on the priority determination condition.

3. The electronic device of claim 2 , wherein the instructions further cause the at least one processor to: compare the at least one value with the priority determination condition, determine a priority for the at least one value, based on a result of the comparison, and select the main information among the at least one value based on the determined priority.

4. The electronic device of claim 3 , wherein the instructions further cause the at least one processor to: when a number of fields of data including the main information exceeds a specified value, exclude a value of at least one field from the selected main information, based on the determined priority.

5. The electronic device of claim 1 , further comprising: an input device, wherein the event comprises entering a natural language input via the input device, and wherein the instructions further cause the at least one processor to: determine an intent corresponding to the natural language input, and determine a parameter for constituting the query based on the determined intent.

6. The electronic device of claim 1 , wherein the context information comprises at least one of user information indicating a feature of a user of the electronic device, time information associated with a point in time when the event occurs, or place information indicating a location of the electronic device.

7. The electronic device of claim 1 , further comprising: a communication circuit configured to communicate with an external electronic device, wherein the instructions further cause the at least one processor to: transmit the query to the external electronic device via the communication circuit, and parse an electronic document received as a response to the query to determine the raw data.

8. The electronic device of claim 1 , wherein the instructions further cause the at least one processor to: select a response template corresponding to the event, and enter the selected main information into the response template to generate the natural language response.

9. The electronic device of claim 8 , wherein the response template comprises a value token capable of being replaced with the main information and a template token branched depending on the context information.

10. A method in which an electronic device provides a natural language response, the method comprising: detecting an occurrence of an event; determining a query corresponding to the event as a response to the occurrence of the event; obtaining raw data based on at least part of the query; determining a main information condition table, from among a plurality of candidate condition tables, based on context information associated with the event, for defining a priority condition; determining the priority condition for selecting data, from among the obtained raw data, based on context information associated with the event and based on the main information condition table; selecting main information from the raw data, based on the priority condition; and outputting a natural language response generated based on the selected main information, wherein the main information condition table comprises at least one data field item and a priority determination condition corresponding to the respective at least one data field item.

11. The method of claim 10 , wherein the selecting of the main information comprises: determining a main information candidate list including at least one value corresponding to the at least one data field item; and selecting the main information among the at least one value based on the priority determination condition.

12. The method of claim 11 , wherein the selecting of the main information among the at least one value comprises: comparing the at least one value with the priority determination condition; determining a priority for the at least one value, based on a result of the comparison; and selecting the main information among the at least one value based on the determined priority.

13. The method of claim 12 , further comprising: when a number of fields of data including the main information exceeds a specified value, excluding a value of at least one field from the selected main information, based on the determined priority.

14. The method of claim 10 , wherein the detecting of the occurrence of the event comprises: receiving a natural language input corresponding to the event, and wherein the determining of the query comprises: determining an intent corresponding to the natural language input, and determining a parameter for constituting the query based on the determined intent.

15. The method of claim 10 , wherein the context information comprises at least one of user information indicating a feature of a user of the electronic device, time information associated with a point in time when the event occurs, or place information indicating a location of the electronic device.

16. The method of claim 10 , wherein the outputting of the natural language response comprises: selecting a response template corresponding to the event; and entering the selected main information into the response template to generate the natural language response.

17. At least one non-transitory computer-readable recording medium having recorded thereon a computer program for executing a method, the method comprising: detecting an occurrence of an event; determining a query corresponding to the event as a response to the occurrence of the event; obtaining raw data based on at least part of the query; determining a main information condition table from among a plurality of candidate condition tables, based on context information associated with the event, for defining a priority condition, determining the priority condition for selecting data, from among the obtained raw data, based on context information associated with the event and based on the main information condition table; selecting main information from the raw data, based on the priority condition; and outputting a natural language response generated based on the selected main information, wherein the main information condition table comprises at least one data field item and a priority determination condition corresponding to the respective at least one data field item.

18. The at least one non-transitory computer-readable recording medium of claim 17 , wherein the context information comprises user information including one of age, personality, hobby, or occupation.